Generative adversarial networks (GANs) with clustered latent spaces can perform conditional generation in a completely unsupervised manner. However, the salient attributes of unlabeled data in the real-world are mostly imbalanced. Existing unsupervised conditional GANs cannot properly cluster the attributes in their latent spaces because they assume uniform distributions of the attributes. To address this problem, we theoretically derive Stein latent optimization that provides reparameterizable gradient estimations of the latent distribution parameters assuming a Gaussian mixture prior in a continuous latent space. Structurally, we introduce an encoder network and a novel contrastive loss to help generated data from a single mixture component to represent a single attribute. We confirm that the proposed method, named Stein Latent Optimization for GANs (SLOGAN), successfully learns the balanced or imbalanced attributes and performs unsupervised tasks such as unsupervised conditional generation, unconditional generation, and cluster assignment even in the absence of information of the attributes (e.g. the imbalance ratio). Moreover, we demonstrate that the attributes to be learned can be manipulated using a small amount of probe data.

翻译：具有集束潜在空间的生成对抗网络(GANs) 能够以完全不受监督的方式产生有条件的生成。 但是,现实世界中未贴标签数据的显著特征大多是不平衡的。 现有的未贴标签的 GANs 无法正确组合其潜在空间中的属性, 因为他们承担了属性的统一分布 。 为了解决这个问题, 我们理论上得出 Stein 潜伏优化, 对潜在分布参数进行可重新量化的梯度估计, 假设在连续潜藏空间中存在高斯混合。 从结构上看, 我们引入了一个编码网络和新的对比性损失, 以帮助从单个混合物组件生成数据来代表一个单一属性。 我们确认, 拟议的方法, 名为 Stein Lenttoptimization for GANs (SLOGAN), 成功学习了平衡或不平衡属性, 并履行了未监控的任务, 如不监管的有条件生成、 无条件生成和集群分配, 甚至在缺少属性信息的情况下( 例如, 不平衡比率 ) 。 此外, 我们证明, 要学习的属性可以使用少量的探测数据来被操纵 。